Proceedings of the 27^th International Conference on Digital Audio Effects (DAFx24)

Guildford, Surrey, UK, September 3-7, 2024

These Proceedings contain the accepted papers from the DAFx24 call for papers in 2024.

DAFx24 is being organised by a team of researchers from the following Institutions:

• University of Surrey, Guildford, UK
• Queen Mary University, London, UK
• University of Edinburgh, Edinburgh, UK

Local Organising Committee:

• Enzo De Sena, chair
• Annika Neidhardt
• Christos Chousidis
• Joshua D. Reiss
• Mark D. Plumbley
• Pedro Llado
• Randall Ali
• Russell Mason
• Stefan Bilbao
• Amal Emthyas
• Joshua Mannall
• Marcela Rada
• Matteo Scerbo
• Natasha Blakemore
• Will J. Cassidy

Website address: https://dafx24.surrey.ac.uk/

Proceedings as a single pdf

Oral Session 1: Deep Learning I

Audio Effect Chain Estimation and Dry Signal Recovery From Multi-Effect-Processed Musical Signals
Osamu Take, Kento Watanabe, Takayuki Nakatsuka, Tian Cheng, Tomoyasu Nakano, Masataka Goto, Shinnosuke Takamichi and Hiroshi Saruwatari

CONMOD: Controllable Neural Frame-Based Modulation Effects
Gyubin Lee, Hounsu Kim, Junwon Lee and Juhan Nam

Sample Rate Independent Recurrent Neural Networks for Audio Effects Processing
Alistair Carson, Alec Wright, Jatin Chowdhury, Vesa Välimäki and Stefan Bilbao

A Diffusion-Based Generative Equalizer for Music Restoration
Eloi Moliner, Maija Turunen, Filip Elvander and Vesa Välimäki

Neural Audio Processing on Android Phones
Jason Hoopes, Brooke Chalmers and Victor Zappi

Poster Session 1: Deep Learning II

RAVE for Speech: Efficient Voice Conversion at High Sampling Rates
Anders R. Bargum and Cumhur Erkut

Network Bending of Diffusion Models for Audio-Visual Generation
Luke Dzwonczyk, Carmine Emanuele Cella and David Ban

Automatic Equalization for Individual Instrument Tracks Using Convolutional Neural Networks
Florian Mockenhaupt, Joscha Simon Rieber and Shahan Nercessian

Balancing Error and Latency of Black-Box Models for Audio Effects Using Hardware-Aware Neural Architecture Search
Christopher Ringhofer, Alexa Gnoss and Gregor Schiele

ICGAN: An Implicit Conditioning Method for Interpretable Feature Control of Neural Audio Synthesis
Yunyi Liu and Craig Jin

A Hierarchical Deep Learning Approach for Minority Instrument Detection
Dylan Sechet, Francesca Bugiotti, Matthieu Kowalski, Edouard D'Hérouville and Filip Langiewicz

Oral Session 2: Virtual Analogue

Wave Digital Model of the MXR Phase 90 Based on a Time-Varying Resistor Approximation of JFET Elements
Riccardo Giampiccolo, Samuele Del Moro, Claudio Eutizi, Mattia Massimi, Oliviero Massi and Alberto Bernardini

Hyper Recurrent Neural Network: Condition Mechanisms for Black-Box Audio Effect Modeling
Yen-Tung Yeh, Wen-Yi Hsiao and Yi-Hsuan Yang

Revisiting the Second-Order Accurate Non-Iterative Discretization Scheme
Martin Holters

Digitizing the Schumann PLL Analog Harmonizer
Isaiah Farrell and Stefan Bilbao

Wave Digital Modeling of Circuits with Multiple One-Port Nonlinearities Based on Lipschitz-Bounded Neural Networks
Oliviero Massi, Edoardo Manino and Alberto Bernardini

Graphic Equalizers Based on Limited Action Networks
Kurt Werner

Poster Session 2: Late Breaking Results

Synthesizer Sound Matching Using Audio Spectrogram Transformers
Fred Bruford, Frederik Blang and Shahan Nercessian

Spectral Analysis of Stochastic Wavetable Synthesis
Nicholas Boyko and Elliot Canfield-Dafilou

Leveraging Electric Guitar Tones and Effects to Improve Robustness in Guitar Tablature Transcription Modeling
Hegel Pedroza, Wallace Abreu, Ryan M. Corey and Iran R. Roman

Oral Session 3: Instrument Modelling and Effects I

Searching for Music Mixing Graphs: A Pruning Approach
Sungho Lee, Marco Martínez-Ramírez, Wei-Hsiang Liao, Stefan Uhlich, Giorgio Fabbro, Kyogu Lee and Yuki Mitsufuji

Quadratic Spline Approximation of the Contact Potential for Real-Time Simulation of Lumped Collisions in Musical Instruments
Abhiram Bhanuprakash, Maarten Van Walstijn and Vasileios Chatziioannou

Real-Time Guitar Synthesis
Stefan Bilbao, Riccardo Russo, Craig Webb and Michele Ducceschi

Guitar Tone Stack Modeling with a Neural State-Space Filter
Tantep Sinjanakhom, Eero-Pekka Damskägg, Stylianos Mimilakis, Athanasios Gotsopoulos and Vesa Välimäki

Distortion Recovery: A Two-Stage Method for Guitar Effect Removal
Ying-Shuo Lee, Yueh-Po Peng, Jui-Te Wu, Ming Cheng, Li Su and Yi-Hsuan Yang

Sound Matching Using Synthesizer Ensembles
Gerard Roma

Poster Session 3: Instrument Modelling and Effects II

Improving Unsupervised Clean-to-Rendered Guitar Tone Transformation Using GANs and Integrated Unaligned Clean Data
Yu-Hua Chen, Woosung Choi, Wei-Hsiang Liao, Marco Martínez-Ramírez, Kin Wai Cheuk, Yuki Mitsufuji, Jyh-Shing Roger Jang and Yi-Hsuan Yang

Towards Efficient Modelling of String Dynamics: A Comparison of State Space and Koopman Based Deep Learning Methods
Rodrigo Diaz, Carlos De La Vega Martin and Mark Sandler

DDSP-Based Neural Waveform Synthesis of Polyphonic Guitar Performance From String-Wise MIDI Input
Nicolas Jonason, Xin Wang, Erica Cooper, Lauri Juvela, Bob L. T. Sturm and Junichi Yamagishi

DDSP-SFX: Acoustically-Guided Sound Effects Generation with Differentiable Digital Signal Processing
Yunyi Liu, Craig Jin and David Gunawan

On Vibrato and Frequency (De)Modulation in Musical Sounds
Jeremy Hyrkas and Tamara Smyth

Oral Session 4: Reverberation I

RIR2FDN: An Improved Room Impulse Response Analysis and Synthesis
Gloria Dal Santo, Benoit Alary, Karolina Prawda, Sebastian Schlecht and Vesa Välimäki

Modeling the Frequency-Dependent Sound Energy Decay of Acoustic Environments with Differentiable Feedback Delay Networks
Alessandro Ilic Mezza, Riccardo Giampiccolo and Alberto Bernardini

Binaural Dark-Velvet-Noise Reverberator
Jon Fagerström, Nils Meyer-Kahlen, Sebastian J. Schlecht and Vesa Välimäki

Differentiable Active Acoustics - Optimizing Stability via Gradient Descent
Gian Marco De Bortoli, Gloria Dal Santo, Karolina Prawda, Tapio Lokki, Vesa Välimäki and Sebastian J. Schlecht

Naturalness of Double-Slope Decay in Generalised Active Acoustic Enhancement Systems
Will Cassidy, Phil Coleman, Russell Mason and Enzo De Sena

A Common-Slopes Late Reverberation Model Based on Acoustic Radiance Transfer
Matteo Scerbo, Sebastian J. Schlecht, Randall Ali, Lauri Savioja and Enzo De Sena

Poster Session 4: Reverberation II

Differentiable MIMO Feedback Delay Networks for Multichannel Room Impulse Response Modeling
Riccardo Giampiccolo, Alessandro Ilic Mezza and Alberto Bernardini

A Highly Parametrized Scattering Delay Network Implementation for Interactive Room Auralization
Marco Fontana, Giorgio Presti, Davide Fantini, Federico Avanzini and Arcadio Reyes-Lecuona

Equalizing Loudspeakers in Reverberant Environments Using Deep Convolutive Dereverberation
Silvio Osimi, Leonardo Gabrielli, Samuele Cornell and Stefano Squartini

Evaluating Neural Networks Architectures for Spring Reverb Modelling
Francesco Papaleo, Xavier Lizarraga-Seijas and Frederic Font

Modified Late Reverberation in an Audio Augmented Reality Scenario
Christian Schneiderwind and Annika Neidhardt

Oral Session 5: Audio Signal Processing I

A Real-Time Approach for Estimating Pulse Tracking Parameters for Beat-Synchronous Audio Effects
Peter Meier, Simon Schwär and Meinard Müller

Parameter Estimation of Frequency-Modulated Sinusoids with the Distribution Derivative Method
Marcelo Caetano

Topology-Preserving Deformations of Digital Audio
Georg Essl

Characterisation and Excursion Modelling of Audio Haptic Transducers
Stephen Oxnard, Ethan Stanhope, Laurence J. Hobden and Mahmoud Masri

Differentiable All-Pole Filters for Time-Varying Audio Systems
Chin-Yun Yu, Christopher Mitcheltree, Alistair Carson, Stefan Bilbao, Joshua Reiss and György Fazekas

Band-Limited Impulse Invariance Method Using Lagrange Kernels
Nara Hahn, Frank Schultz and Sascha Spors

Poster Session 5: Audio Signal Processing II

Interpolation Filters for Antiderivative Antialiasing
Victor Zheleznov and Stefan Bilbao

PIPES: A Networked Rapid Development Protocol for Sound Applications
Paolo Marrone, Stefano D'Angelo and Federico Fontana

Audio Visualization via Delay Embedding and Subspace Learning
Alois Cerbu and Carmine Cella

Real-Time System for Sound Enhancement in Noisy Environment
Stefania Cecchi, Valeria Bruschi, Paolo Peretti and Ferruccio Bettarelli

Hybrid Audio Inpainting Approach with Structured Sparse Decomposition and Sinusoidal Modeling
Eto Sun and Philippe Depalle

Oral Session 6: Spatial Audio

HRTF Spatial Upsampling in the Spherical Harmonics Domain Employing a Generative Adversarial Network
Xuyi Hu, Jian Li, Lorenzo Picinali and Aidan Hogg

NBU: Neural Binaural Upmixing of Stereo Content
Philipp Grundhuber, Michael Lovedee-Turner and Emanuël Habets

Frequency-Dependent Characteristics and Perceptual Validation of the Interaural Thresholded Level Distribution
Christian S. E. Cotton, Stephen G. Oxnard, Laurence J. Hobden and Ethan Stanhope

Decoding Sound Source Location From EEG: Preliminary Comparisons of Spatial Rendering and Location
Nils Marggraf-Turley, Lorenzo Picinali, Niels Pontoppidan, Martha Shiell and Drew Cappotto

A Deep Learning Approach to the Prediction of Time-Frequency Spatial Parameters for Use in Stereo Upmixing
Daniel Turner and Damian Murphy

Audio-Visual Talker Localization in Video for Spatial Sound Reproduction
Davide Berghi and Philip Jackson

Poster Session 6: Demos and Software

QUBX: Rust Library for Queue-Based Multithreaded Real-Time Parallel Audio Streams Processing and Management
Pasquale Mainolfi

GPGPU Audio Benchmark Framework
Travis Skare

Real-Time Implementation of a Linear-Phase Octave Graphic Equalizer
Valeria Bruschi, Stefania Cecchi, Alessandro Nicolini and Vesa Välimäki

An Open Source Stereo Widening Plugin
Orchisama Das

GRAFX: An Open-Source Library for Audio Processing Graphs in Pytorch
Sungho Lee, Marco Martínez-Ramírez, Wei-Hsiang Liao, Stefan Uhlich, Giorgio Fabbro, Kyogu Lee and Yuki Mitsufuji

LTFATPY: Towards Making a Wide Range of Time-Frequency Representations Available in Python
Clara Hollomey and Nicki Holighaus